Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources. The redundancy in feature maps is an important characteristic of those successful CNNs, but has rarely been investigated in neural architecture design. This paper proposes a novel Ghost module to generate more feature maps from cheap operations. Based on a set of intrinsic feature maps, we apply a series of linear transformations with cheap cost to generate many ghost feature maps that could fully reveal information underlying intrinsic features.
2019: Kai Han, Yunhe Wang, Qi Tian, Jianyuan Guo, Chunjing Xu, Chang Xu
https://arxiv.org/pdf/1911.11907v2.pdf
Quantifying Language Models’ Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
Large Language Models for Generative Information Extraction: A Survey
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Soaring from 4K to 400K: Extending LLM’s Context with Activation Beacon
Parameter-Efficient Transfer Learning for NLP
Mixtral of Experts
MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts
WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia
Video Understanding with Large Language Models: A Survey
GPT-4V(ision) is a Generalist Web Agent, if Grounded
TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
AnyText: Multilingual Visual Text Generation And Editing
KwaiAgents: Generalized Information-seeking Agent System with Large Language Models
Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4
Fast Inference of Mixture-of-Experts Language Models with Offloading
Retrieval-Augmented Generation for Large Language Models: A Survey
PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
Pearl: A Production-ready Reinforcement Learning Agent
Are Emergent Abilities in Large Language Models just In-Context Learning?
Join Podbean Ads Marketplace and connect with engaged listeners.
Advertise Today
Create your
podcast in
minutes
It is Free
WSJ Tech News Briefing
Rebel Tech
The 404 Media Podcast
CyberWire Daily
Cyber Security Headlines